fix(honcho): isolate session routing for multi-user gateway (#1500)
Salvaged from PR #1470 by adavyas. Core fix: Honcho tool calls in a multi-session gateway could route to the wrong session because honcho_tools.py relied on process-global state. Now threads session context through the call chain: AIAgent._invoke_tool() → handle_function_call() → registry.dispatch() → handler **kw → _resolve_session_context() Changes: - Add _resolve_session_context() to prefer per-call context over globals - Plumb honcho_manager + honcho_session_key through handle_function_call - Add sync_honcho=False to run_conversation() for synthetic flush turns - Pass honcho_session_key through gateway memory flush lifecycle - Harden gateway PID detection when /proc cmdline is unreadable - Make interrupt test scripts import-safe for pytest-xdist - Wrap BibTeX examples in Jekyll raw blocks for docs build - Fix thread-order-dependent assertion in client lifecycle test - Expand Honcho docs: session isolation, lifecycle, routing internals Dropped from original PR: - Indentation change in _create_request_openai_client that would move client creation inside the lock (causes unnecessary contention) Co-authored-by: adavyas <adavyas@users.noreply.github.com>
This commit is contained in:
Teknium
GitHub
parent
eb4f0348e1
commit
dd7921d514
17 changed files with 522 additions and 252 deletions
|
|
@ -90,6 +90,7 @@ class TestGatewayHonchoLifecycle:
|
|||
runner = _make_runner()
|
||||
event = _make_event()
|
||||
runner._shutdown_gateway_honcho = MagicMock()
|
||||
runner._async_flush_memories = AsyncMock()
|
||||
runner.session_store = MagicMock()
|
||||
runner.session_store._generate_session_key.return_value = "gateway-key"
|
||||
runner.session_store._entries = {
|
||||
|
|
@ -100,4 +101,31 @@ class TestGatewayHonchoLifecycle:
|
|||
result = await runner._handle_reset_command(event)
|
||||
|
||||
runner._shutdown_gateway_honcho.assert_called_once_with("gateway-key")
|
||||
runner._async_flush_memories.assert_called_once_with("old-session", "gateway-key")
|
||||
assert "Session reset" in result
|
||||
|
||||
def test_flush_memories_reuses_gateway_session_key_and_skips_honcho_sync(self):
|
||||
runner = _make_runner()
|
||||
runner.session_store = MagicMock()
|
||||
runner.session_store.load_transcript.return_value = [
|
||||
{"role": "user", "content": "a"},
|
||||
{"role": "assistant", "content": "b"},
|
||||
{"role": "user", "content": "c"},
|
||||
{"role": "assistant", "content": "d"},
|
||||
]
|
||||
tmp_agent = MagicMock()
|
||||
|
||||
with (
|
||||
patch("gateway.run._resolve_runtime_agent_kwargs", return_value={"api_key": "test-key"}),
|
||||
patch("gateway.run._resolve_gateway_model", return_value="model-name"),
|
||||
patch("run_agent.AIAgent", return_value=tmp_agent) as mock_agent_cls,
|
||||
):
|
||||
runner._flush_memories_for_session("old-session", "gateway-key")
|
||||
|
||||
mock_agent_cls.assert_called_once()
|
||||
_, kwargs = mock_agent_cls.call_args
|
||||
assert kwargs["session_id"] == "old-session"
|
||||
assert kwargs["honcho_session_key"] == "gateway-key"
|
||||
tmp_agent.run_conversation.assert_called_once()
|
||||
_, run_kwargs = tmp_agent.run_conversation.call_args
|
||||
assert run_kwargs["sync_honcho"] is False
|
||||
|
|
|
|||
|
|
@ -199,3 +199,28 @@ class TestHandleResumeCommand:
|
|||
|
||||
assert real_key not in runner._running_agents
|
||||
db.close()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_resume_flushes_memories_with_gateway_session_key(self, tmp_path):
|
||||
"""Resume should preserve the gateway session key for Honcho flushes."""
|
||||
from hermes_state import SessionDB
|
||||
|
||||
db = SessionDB(db_path=tmp_path / "state.db")
|
||||
db.create_session("old_session", "telegram")
|
||||
db.set_session_title("old_session", "Old Work")
|
||||
db.create_session("current_session_001", "telegram")
|
||||
|
||||
event = _make_event(text="/resume Old Work")
|
||||
runner = _make_runner(
|
||||
session_db=db,
|
||||
current_session_id="current_session_001",
|
||||
event=event,
|
||||
)
|
||||
|
||||
await runner._handle_resume_command(event)
|
||||
|
||||
runner._async_flush_memories.assert_called_once_with(
|
||||
"current_session_001",
|
||||
_session_key_for_event(event),
|
||||
)
|
||||
db.close()
|
||||
|
|
|
|||
|
|
@ -26,6 +26,22 @@ class TestGatewayPidState:
|
|||
assert status.get_running_pid() is None
|
||||
assert not pid_path.exists()
|
||||
|
||||
def test_get_running_pid_accepts_gateway_metadata_when_cmdline_unavailable(self, tmp_path, monkeypatch):
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
pid_path = tmp_path / "gateway.pid"
|
||||
pid_path.write_text(json.dumps({
|
||||
"pid": os.getpid(),
|
||||
"kind": "hermes-gateway",
|
||||
"argv": ["python", "-m", "hermes_cli.main", "gateway"],
|
||||
"start_time": 123,
|
||||
}))
|
||||
|
||||
monkeypatch.setattr(status.os, "kill", lambda pid, sig: None)
|
||||
monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
|
||||
monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
|
||||
|
||||
assert status.get_running_pid() == os.getpid()
|
||||
|
||||
|
||||
class TestGatewayRuntimeStatus:
|
||||
def test_write_runtime_status_records_platform_failure(self, tmp_path, monkeypatch):
|
||||
|
|
|
|||
|
|
@ -16,126 +16,131 @@ from run_agent import AIAgent, IterationBudget
|
|||
from tools.delegate_tool import _run_single_child
|
||||
from tools.interrupt import set_interrupt, is_interrupted
|
||||
|
||||
set_interrupt(False)
|
||||
def main() -> int:
|
||||
set_interrupt(False)
|
||||
|
||||
# Create parent agent (minimal)
|
||||
parent = AIAgent.__new__(AIAgent)
|
||||
parent._interrupt_requested = False
|
||||
parent._interrupt_message = None
|
||||
parent._active_children = []
|
||||
parent.quiet_mode = True
|
||||
parent.model = "test/model"
|
||||
parent.base_url = "http://localhost:1"
|
||||
parent.api_key = "test"
|
||||
parent.provider = "test"
|
||||
parent.api_mode = "chat_completions"
|
||||
parent.platform = "cli"
|
||||
parent.enabled_toolsets = ["terminal", "file"]
|
||||
parent.providers_allowed = None
|
||||
parent.providers_ignored = None
|
||||
parent.providers_order = None
|
||||
parent.provider_sort = None
|
||||
parent.max_tokens = None
|
||||
parent.reasoning_config = None
|
||||
parent.prefill_messages = None
|
||||
parent._session_db = None
|
||||
parent._delegate_depth = 0
|
||||
parent._delegate_spinner = None
|
||||
parent.tool_progress_callback = None
|
||||
parent.iteration_budget = IterationBudget(max_total=100)
|
||||
parent._client_kwargs = {"api_key": "test", "base_url": "http://localhost:1"}
|
||||
# Create parent agent (minimal)
|
||||
parent = AIAgent.__new__(AIAgent)
|
||||
parent._interrupt_requested = False
|
||||
parent._interrupt_message = None
|
||||
parent._active_children = []
|
||||
parent.quiet_mode = True
|
||||
parent.model = "test/model"
|
||||
parent.base_url = "http://localhost:1"
|
||||
parent.api_key = "test"
|
||||
parent.provider = "test"
|
||||
parent.api_mode = "chat_completions"
|
||||
parent.platform = "cli"
|
||||
parent.enabled_toolsets = ["terminal", "file"]
|
||||
parent.providers_allowed = None
|
||||
parent.providers_ignored = None
|
||||
parent.providers_order = None
|
||||
parent.provider_sort = None
|
||||
parent.max_tokens = None
|
||||
parent.reasoning_config = None
|
||||
parent.prefill_messages = None
|
||||
parent._session_db = None
|
||||
parent._delegate_depth = 0
|
||||
parent._delegate_spinner = None
|
||||
parent.tool_progress_callback = None
|
||||
parent.iteration_budget = IterationBudget(max_total=100)
|
||||
parent._client_kwargs = {"api_key": "test", "base_url": "http://localhost:1"}
|
||||
|
||||
child_started = threading.Event()
|
||||
result_holder = [None]
|
||||
child_started = threading.Event()
|
||||
result_holder = [None]
|
||||
|
||||
def run_delegate():
|
||||
with patch("run_agent.OpenAI") as MockOpenAI:
|
||||
mock_client = MagicMock()
|
||||
|
||||
def run_delegate():
|
||||
with patch("run_agent.OpenAI") as MockOpenAI:
|
||||
mock_client = MagicMock()
|
||||
def slow_create(**kwargs):
|
||||
time.sleep(3)
|
||||
resp = MagicMock()
|
||||
resp.choices = [MagicMock()]
|
||||
resp.choices[0].message.content = "Done"
|
||||
resp.choices[0].message.tool_calls = None
|
||||
resp.choices[0].message.refusal = None
|
||||
resp.choices[0].finish_reason = "stop"
|
||||
resp.usage.prompt_tokens = 100
|
||||
resp.usage.completion_tokens = 10
|
||||
resp.usage.total_tokens = 110
|
||||
resp.usage.prompt_tokens_details = None
|
||||
return resp
|
||||
|
||||
def slow_create(**kwargs):
|
||||
time.sleep(3)
|
||||
resp = MagicMock()
|
||||
resp.choices = [MagicMock()]
|
||||
resp.choices[0].message.content = "Done"
|
||||
resp.choices[0].message.tool_calls = None
|
||||
resp.choices[0].message.refusal = None
|
||||
resp.choices[0].finish_reason = "stop"
|
||||
resp.usage.prompt_tokens = 100
|
||||
resp.usage.completion_tokens = 10
|
||||
resp.usage.total_tokens = 110
|
||||
resp.usage.prompt_tokens_details = None
|
||||
return resp
|
||||
mock_client.chat.completions.create = slow_create
|
||||
mock_client.close = MagicMock()
|
||||
MockOpenAI.return_value = mock_client
|
||||
|
||||
mock_client.chat.completions.create = slow_create
|
||||
mock_client.close = MagicMock()
|
||||
MockOpenAI.return_value = mock_client
|
||||
original_init = AIAgent.__init__
|
||||
|
||||
original_init = AIAgent.__init__
|
||||
def patched_init(self_agent, *a, **kw):
|
||||
original_init(self_agent, *a, **kw)
|
||||
child_started.set()
|
||||
|
||||
def patched_init(self_agent, *a, **kw):
|
||||
original_init(self_agent, *a, **kw)
|
||||
child_started.set()
|
||||
with patch.object(AIAgent, "__init__", patched_init):
|
||||
try:
|
||||
result = _run_single_child(
|
||||
task_index=0,
|
||||
goal="Test slow task",
|
||||
context=None,
|
||||
toolsets=["terminal"],
|
||||
model="test/model",
|
||||
max_iterations=5,
|
||||
parent_agent=parent,
|
||||
task_count=1,
|
||||
override_provider="test",
|
||||
override_base_url="http://localhost:1",
|
||||
override_api_key="test",
|
||||
override_api_mode="chat_completions",
|
||||
)
|
||||
result_holder[0] = result
|
||||
except Exception as e:
|
||||
print(f"ERROR in delegate: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
|
||||
with patch.object(AIAgent, "__init__", patched_init):
|
||||
try:
|
||||
result = _run_single_child(
|
||||
task_index=0,
|
||||
goal="Test slow task",
|
||||
context=None,
|
||||
toolsets=["terminal"],
|
||||
model="test/model",
|
||||
max_iterations=5,
|
||||
parent_agent=parent,
|
||||
task_count=1,
|
||||
override_provider="test",
|
||||
override_base_url="http://localhost:1",
|
||||
override_api_key="test",
|
||||
override_api_mode="chat_completions",
|
||||
)
|
||||
result_holder[0] = result
|
||||
except Exception as e:
|
||||
print(f"ERROR in delegate: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
print("Starting agent thread...")
|
||||
agent_thread = threading.Thread(target=run_delegate, daemon=True)
|
||||
agent_thread.start()
|
||||
|
||||
started = child_started.wait(timeout=10)
|
||||
if not started:
|
||||
print("ERROR: Child never started")
|
||||
set_interrupt(False)
|
||||
return 1
|
||||
|
||||
print("Starting agent thread...")
|
||||
agent_thread = threading.Thread(target=run_delegate, daemon=True)
|
||||
agent_thread.start()
|
||||
time.sleep(0.5)
|
||||
|
||||
started = child_started.wait(timeout=10)
|
||||
if not started:
|
||||
print("ERROR: Child never started")
|
||||
sys.exit(1)
|
||||
print(f"Active children: {len(parent._active_children)}")
|
||||
for i, c in enumerate(parent._active_children):
|
||||
print(f" Child {i}: _interrupt_requested={c._interrupt_requested}")
|
||||
|
||||
time.sleep(0.5)
|
||||
t0 = time.monotonic()
|
||||
parent.interrupt("User typed a new message")
|
||||
print("Called parent.interrupt()")
|
||||
|
||||
print(f"Active children: {len(parent._active_children)}")
|
||||
for i, c in enumerate(parent._active_children):
|
||||
print(f" Child {i}: _interrupt_requested={c._interrupt_requested}")
|
||||
for i, c in enumerate(parent._active_children):
|
||||
print(f" Child {i} after interrupt: _interrupt_requested={c._interrupt_requested}")
|
||||
print(f"Global is_interrupted: {is_interrupted()}")
|
||||
|
||||
t0 = time.monotonic()
|
||||
parent.interrupt("User typed a new message")
|
||||
print(f"Called parent.interrupt()")
|
||||
agent_thread.join(timeout=10)
|
||||
elapsed = time.monotonic() - t0
|
||||
print(f"Agent thread finished in {elapsed:.2f}s")
|
||||
|
||||
for i, c in enumerate(parent._active_children):
|
||||
print(f" Child {i} after interrupt: _interrupt_requested={c._interrupt_requested}")
|
||||
print(f"Global is_interrupted: {is_interrupted()}")
|
||||
|
||||
agent_thread.join(timeout=10)
|
||||
elapsed = time.monotonic() - t0
|
||||
print(f"Agent thread finished in {elapsed:.2f}s")
|
||||
|
||||
result = result_holder[0]
|
||||
if result:
|
||||
print(f"Status: {result['status']}")
|
||||
print(f"Duration: {result['duration_seconds']}s")
|
||||
if elapsed < 2.0:
|
||||
print("✅ PASS: Interrupt detected quickly!")
|
||||
result = result_holder[0]
|
||||
if result:
|
||||
print(f"Status: {result['status']}")
|
||||
print(f"Duration: {result['duration_seconds']}s")
|
||||
if elapsed < 2.0:
|
||||
print("✅ PASS: Interrupt detected quickly!")
|
||||
else:
|
||||
print(f"❌ FAIL: Took {elapsed:.2f}s — interrupt was too slow or not detected")
|
||||
else:
|
||||
print(f"❌ FAIL: Took {elapsed:.2f}s — interrupt was too slow or not detected")
|
||||
else:
|
||||
print("❌ FAIL: No result!")
|
||||
print("❌ FAIL: No result!")
|
||||
|
||||
set_interrupt(False)
|
||||
set_interrupt(False)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
|
|
|
|||
|
|
@ -29,51 +29,6 @@ from unittest.mock import MagicMock, patch
|
|||
from run_agent import AIAgent, IterationBudget
|
||||
from tools.interrupt import set_interrupt, is_interrupted
|
||||
|
||||
set_interrupt(False)
|
||||
|
||||
# ─── Create parent agent ───
|
||||
parent = AIAgent.__new__(AIAgent)
|
||||
parent._interrupt_requested = False
|
||||
parent._interrupt_message = None
|
||||
parent._active_children = []
|
||||
parent.quiet_mode = True
|
||||
parent.model = "test/model"
|
||||
parent.base_url = "http://localhost:1"
|
||||
parent.api_key = "test"
|
||||
parent.provider = "test"
|
||||
parent.api_mode = "chat_completions"
|
||||
parent.platform = "cli"
|
||||
parent.enabled_toolsets = ["terminal", "file"]
|
||||
parent.providers_allowed = None
|
||||
parent.providers_ignored = None
|
||||
parent.providers_order = None
|
||||
parent.provider_sort = None
|
||||
parent.max_tokens = None
|
||||
parent.reasoning_config = None
|
||||
parent.prefill_messages = None
|
||||
parent._session_db = None
|
||||
parent._delegate_depth = 0
|
||||
parent._delegate_spinner = None
|
||||
parent.tool_progress_callback = None
|
||||
parent.iteration_budget = IterationBudget(max_total=100)
|
||||
parent._client_kwargs = {"api_key": "test", "base_url": "http://localhost:1"}
|
||||
|
||||
# Monkey-patch parent.interrupt to log
|
||||
_original_interrupt = AIAgent.interrupt
|
||||
def logged_interrupt(self, message=None):
|
||||
log.info(f"🔴 parent.interrupt() called with: {message!r}")
|
||||
log.info(f" _active_children count: {len(self._active_children)}")
|
||||
_original_interrupt(self, message)
|
||||
log.info(f" After interrupt: _interrupt_requested={self._interrupt_requested}")
|
||||
for i, c in enumerate(self._active_children):
|
||||
log.info(f" Child {i}._interrupt_requested={c._interrupt_requested}")
|
||||
parent.interrupt = lambda msg=None: logged_interrupt(parent, msg)
|
||||
|
||||
# ─── Simulate the exact CLI flow ───
|
||||
interrupt_queue = queue.Queue()
|
||||
child_running = threading.Event()
|
||||
agent_result = [None]
|
||||
|
||||
def make_slow_response(delay=2.0):
|
||||
"""API response that takes a while."""
|
||||
def create(**kwargs):
|
||||
|
|
@ -94,96 +49,154 @@ def make_slow_response(delay=2.0):
|
|||
return create
|
||||
|
||||
|
||||
def agent_thread_func():
|
||||
"""Simulates the agent_thread in cli.py's chat() method."""
|
||||
log.info("🟢 agent_thread starting")
|
||||
def main() -> int:
|
||||
set_interrupt(False)
|
||||
|
||||
with patch("run_agent.OpenAI") as MockOpenAI:
|
||||
mock_client = MagicMock()
|
||||
mock_client.chat.completions.create = make_slow_response(delay=3.0)
|
||||
mock_client.close = MagicMock()
|
||||
MockOpenAI.return_value = mock_client
|
||||
# ─── Create parent agent ───
|
||||
parent = AIAgent.__new__(AIAgent)
|
||||
parent._interrupt_requested = False
|
||||
parent._interrupt_message = None
|
||||
parent._active_children = []
|
||||
parent.quiet_mode = True
|
||||
parent.model = "test/model"
|
||||
parent.base_url = "http://localhost:1"
|
||||
parent.api_key = "test"
|
||||
parent.provider = "test"
|
||||
parent.api_mode = "chat_completions"
|
||||
parent.platform = "cli"
|
||||
parent.enabled_toolsets = ["terminal", "file"]
|
||||
parent.providers_allowed = None
|
||||
parent.providers_ignored = None
|
||||
parent.providers_order = None
|
||||
parent.provider_sort = None
|
||||
parent.max_tokens = None
|
||||
parent.reasoning_config = None
|
||||
parent.prefill_messages = None
|
||||
parent._session_db = None
|
||||
parent._delegate_depth = 0
|
||||
parent._delegate_spinner = None
|
||||
parent.tool_progress_callback = None
|
||||
parent.iteration_budget = IterationBudget(max_total=100)
|
||||
parent._client_kwargs = {"api_key": "test", "base_url": "http://localhost:1"}
|
||||
|
||||
from tools.delegate_tool import _run_single_child
|
||||
# Monkey-patch parent.interrupt to log
|
||||
_original_interrupt = AIAgent.interrupt
|
||||
|
||||
# Signal that child is about to start
|
||||
original_init = AIAgent.__init__
|
||||
def patched_init(self_agent, *a, **kw):
|
||||
log.info("🟡 Child AIAgent.__init__ called")
|
||||
original_init(self_agent, *a, **kw)
|
||||
child_running.set()
|
||||
log.info(f"🟡 Child started, parent._active_children = {len(parent._active_children)}")
|
||||
def logged_interrupt(self, message=None):
|
||||
log.info(f"🔴 parent.interrupt() called with: {message!r}")
|
||||
log.info(f" _active_children count: {len(self._active_children)}")
|
||||
_original_interrupt(self, message)
|
||||
log.info(f" After interrupt: _interrupt_requested={self._interrupt_requested}")
|
||||
for i, child in enumerate(self._active_children):
|
||||
log.info(f" Child {i}._interrupt_requested={child._interrupt_requested}")
|
||||
|
||||
with patch.object(AIAgent, "__init__", patched_init):
|
||||
result = _run_single_child(
|
||||
task_index=0,
|
||||
goal="Do a slow thing",
|
||||
context=None,
|
||||
toolsets=["terminal"],
|
||||
model="test/model",
|
||||
max_iterations=3,
|
||||
parent_agent=parent,
|
||||
task_count=1,
|
||||
override_provider="test",
|
||||
override_base_url="http://localhost:1",
|
||||
override_api_key="test",
|
||||
override_api_mode="chat_completions",
|
||||
)
|
||||
agent_result[0] = result
|
||||
log.info(f"🟢 agent_thread finished. Result status: {result.get('status')}")
|
||||
parent.interrupt = lambda msg=None: logged_interrupt(parent, msg)
|
||||
|
||||
# ─── Simulate the exact CLI flow ───
|
||||
interrupt_queue = queue.Queue()
|
||||
child_running = threading.Event()
|
||||
agent_result = [None]
|
||||
|
||||
# ─── Start agent thread (like chat() does) ───
|
||||
agent_thread = threading.Thread(target=agent_thread_func, name="agent_thread", daemon=True)
|
||||
agent_thread.start()
|
||||
def agent_thread_func():
|
||||
"""Simulates the agent_thread in cli.py's chat() method."""
|
||||
log.info("🟢 agent_thread starting")
|
||||
|
||||
# ─── Wait for child to start ───
|
||||
if not child_running.wait(timeout=10):
|
||||
print("FAIL: Child never started", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
with patch("run_agent.OpenAI") as MockOpenAI:
|
||||
mock_client = MagicMock()
|
||||
mock_client.chat.completions.create = make_slow_response(delay=3.0)
|
||||
mock_client.close = MagicMock()
|
||||
MockOpenAI.return_value = mock_client
|
||||
|
||||
# Give child time to enter its main loop and start API call
|
||||
time.sleep(1.0)
|
||||
from tools.delegate_tool import _run_single_child
|
||||
|
||||
# ─── Simulate user typing a message (like handle_enter does) ───
|
||||
log.info("📝 Simulating user typing 'Hey stop that'")
|
||||
interrupt_queue.put("Hey stop that")
|
||||
# Signal that child is about to start
|
||||
original_init = AIAgent.__init__
|
||||
|
||||
# ─── Simulate chat() polling loop (like the real chat() method) ───
|
||||
log.info("📡 Starting interrupt queue polling (like chat())")
|
||||
interrupt_msg = None
|
||||
poll_count = 0
|
||||
while agent_thread.is_alive():
|
||||
try:
|
||||
interrupt_msg = interrupt_queue.get(timeout=0.1)
|
||||
if interrupt_msg:
|
||||
log.info(f"📨 Got interrupt message from queue: {interrupt_msg!r}")
|
||||
log.info(f" Calling parent.interrupt()...")
|
||||
parent.interrupt(interrupt_msg)
|
||||
log.info(f" parent.interrupt() returned. Breaking poll loop.")
|
||||
break
|
||||
except queue.Empty:
|
||||
poll_count += 1
|
||||
if poll_count % 20 == 0: # Log every 2s
|
||||
log.info(f" Still polling ({poll_count} iterations)...")
|
||||
def patched_init(self_agent, *a, **kw):
|
||||
log.info("🟡 Child AIAgent.__init__ called")
|
||||
original_init(self_agent, *a, **kw)
|
||||
child_running.set()
|
||||
log.info(
|
||||
f"🟡 Child started, parent._active_children = {len(parent._active_children)}"
|
||||
)
|
||||
|
||||
# ─── Wait for agent to finish ───
|
||||
log.info("⏳ Waiting for agent_thread to join...")
|
||||
t0 = time.monotonic()
|
||||
agent_thread.join(timeout=10)
|
||||
elapsed = time.monotonic() - t0
|
||||
log.info(f"✅ agent_thread joined after {elapsed:.2f}s")
|
||||
with patch.object(AIAgent, "__init__", patched_init):
|
||||
result = _run_single_child(
|
||||
task_index=0,
|
||||
goal="Do a slow thing",
|
||||
context=None,
|
||||
toolsets=["terminal"],
|
||||
model="test/model",
|
||||
max_iterations=3,
|
||||
parent_agent=parent,
|
||||
task_count=1,
|
||||
override_provider="test",
|
||||
override_base_url="http://localhost:1",
|
||||
override_api_key="test",
|
||||
override_api_mode="chat_completions",
|
||||
)
|
||||
agent_result[0] = result
|
||||
log.info(f"🟢 agent_thread finished. Result status: {result.get('status')}")
|
||||
|
||||
# ─── Check results ───
|
||||
result = agent_result[0]
|
||||
if result:
|
||||
log.info(f"Result status: {result['status']}")
|
||||
log.info(f"Result duration: {result['duration_seconds']}s")
|
||||
if result["status"] == "interrupted" and elapsed < 2.0:
|
||||
print("✅ PASS: Interrupt worked correctly!", file=sys.stderr)
|
||||
else:
|
||||
# ─── Start agent thread (like chat() does) ───
|
||||
agent_thread = threading.Thread(target=agent_thread_func, name="agent_thread", daemon=True)
|
||||
agent_thread.start()
|
||||
|
||||
# ─── Wait for child to start ───
|
||||
if not child_running.wait(timeout=10):
|
||||
print("FAIL: Child never started", file=sys.stderr)
|
||||
set_interrupt(False)
|
||||
return 1
|
||||
|
||||
# Give child time to enter its main loop and start API call
|
||||
time.sleep(1.0)
|
||||
|
||||
# ─── Simulate user typing a message (like handle_enter does) ───
|
||||
log.info("📝 Simulating user typing 'Hey stop that'")
|
||||
interrupt_queue.put("Hey stop that")
|
||||
|
||||
# ─── Simulate chat() polling loop (like the real chat() method) ───
|
||||
log.info("📡 Starting interrupt queue polling (like chat())")
|
||||
interrupt_msg = None
|
||||
poll_count = 0
|
||||
while agent_thread.is_alive():
|
||||
try:
|
||||
interrupt_msg = interrupt_queue.get(timeout=0.1)
|
||||
if interrupt_msg:
|
||||
log.info(f"📨 Got interrupt message from queue: {interrupt_msg!r}")
|
||||
log.info(" Calling parent.interrupt()...")
|
||||
parent.interrupt(interrupt_msg)
|
||||
log.info(" parent.interrupt() returned. Breaking poll loop.")
|
||||
break
|
||||
except queue.Empty:
|
||||
poll_count += 1
|
||||
if poll_count % 20 == 0: # Log every 2s
|
||||
log.info(f" Still polling ({poll_count} iterations)...")
|
||||
|
||||
# ─── Wait for agent to finish ───
|
||||
log.info("⏳ Waiting for agent_thread to join...")
|
||||
t0 = time.monotonic()
|
||||
agent_thread.join(timeout=10)
|
||||
elapsed = time.monotonic() - t0
|
||||
log.info(f"✅ agent_thread joined after {elapsed:.2f}s")
|
||||
|
||||
# ─── Check results ───
|
||||
result = agent_result[0]
|
||||
if result:
|
||||
log.info(f"Result status: {result['status']}")
|
||||
log.info(f"Result duration: {result['duration_seconds']}s")
|
||||
if result["status"] == "interrupted" and elapsed < 2.0:
|
||||
print("✅ PASS: Interrupt worked correctly!", file=sys.stderr)
|
||||
set_interrupt(False)
|
||||
return 0
|
||||
print(f"❌ FAIL: status={result['status']}, elapsed={elapsed:.2f}s", file=sys.stderr)
|
||||
else:
|
||||
print("❌ FAIL: No result returned", file=sys.stderr)
|
||||
set_interrupt(False)
|
||||
return 1
|
||||
|
||||
set_interrupt(False)
|
||||
print("❌ FAIL: No result returned", file=sys.stderr)
|
||||
set_interrupt(False)
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
|
|
|
|||
|
|
@ -145,8 +145,9 @@ def test_concurrent_requests_do_not_break_each_other_when_one_client_closes(monk
|
|||
thread_one.join(timeout=5)
|
||||
thread_two.join(timeout=5)
|
||||
|
||||
assert isinstance(results["first"], APIConnectionError)
|
||||
assert results["second"] == {"ok": "second"}
|
||||
values = list(results.values())
|
||||
assert sum(isinstance(value, APIConnectionError) for value in values) == 1
|
||||
assert values.count({"ok": "second"}) == 1
|
||||
assert len(factory.calls) == 2
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -930,8 +930,10 @@ class TestConcurrentToolExecution:
|
|||
mock_hfc.assert_called_once_with(
|
||||
"web_search", {"q": "test"}, "task-1",
|
||||
enabled_tools=list(agent.valid_tool_names),
|
||||
honcho_manager=None,
|
||||
honcho_session_key=None,
|
||||
)
|
||||
assert result == "result"
|
||||
assert result == "result"
|
||||
|
||||
def test_invoke_tool_handles_agent_level_tools(self, agent):
|
||||
"""_invoke_tool should handle todo tool directly."""
|
||||
|
|
@ -1584,6 +1586,38 @@ class TestSystemPromptStability:
|
|||
should_prefetch = not conversation_history
|
||||
assert should_prefetch is True
|
||||
|
||||
def test_run_conversation_can_skip_honcho_sync_for_synthetic_turns(self, agent):
|
||||
captured = {}
|
||||
|
||||
def _fake_api_call(api_kwargs):
|
||||
captured.update(api_kwargs)
|
||||
return _mock_response(content="done", finish_reason="stop")
|
||||
|
||||
agent._honcho = MagicMock()
|
||||
agent._honcho_session_key = "session-1"
|
||||
agent._honcho_config = SimpleNamespace(
|
||||
ai_peer="hermes",
|
||||
memory_mode="hybrid",
|
||||
write_frequency="async",
|
||||
recall_mode="hybrid",
|
||||
)
|
||||
agent._use_prompt_caching = False
|
||||
|
||||
with (
|
||||
patch.object(agent, "_honcho_sync") as mock_sync,
|
||||
patch.object(agent, "_queue_honcho_prefetch") as mock_prefetch,
|
||||
patch.object(agent, "_persist_session"),
|
||||
patch.object(agent, "_save_trajectory"),
|
||||
patch.object(agent, "_cleanup_task_resources"),
|
||||
patch.object(agent, "_interruptible_api_call", side_effect=_fake_api_call),
|
||||
):
|
||||
result = agent.run_conversation("synthetic flush turn", sync_honcho=False)
|
||||
|
||||
assert result["completed"] is True
|
||||
assert captured["messages"][-1]["content"] == "synthetic flush turn"
|
||||
mock_sync.assert_not_called()
|
||||
mock_prefetch.assert_not_called()
|
||||
|
||||
|
||||
class TestHonchoActivation:
|
||||
def test_disabled_config_skips_honcho_init(self):
|
||||
|
|
|
|||
36
tests/tools/test_honcho_tools.py
Normal file
36
tests/tools/test_honcho_tools.py
Normal file
|
|
@ -0,0 +1,36 @@
|
|||
"""Regression tests for per-call Honcho tool session routing."""
|
||||
|
||||
import json
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
from tools import honcho_tools
|
||||
|
||||
|
||||
class TestHonchoToolSessionContext:
|
||||
def setup_method(self):
|
||||
self.orig_manager = honcho_tools._session_manager
|
||||
self.orig_key = honcho_tools._session_key
|
||||
|
||||
def teardown_method(self):
|
||||
honcho_tools._session_manager = self.orig_manager
|
||||
honcho_tools._session_key = self.orig_key
|
||||
|
||||
def test_explicit_call_context_wins_over_module_global_state(self):
|
||||
global_manager = MagicMock()
|
||||
global_manager.get_peer_card.return_value = ["global"]
|
||||
explicit_manager = MagicMock()
|
||||
explicit_manager.get_peer_card.return_value = ["explicit"]
|
||||
|
||||
honcho_tools.set_session_context(global_manager, "global-session")
|
||||
|
||||
result = json.loads(
|
||||
honcho_tools._handle_honcho_profile(
|
||||
{},
|
||||
honcho_manager=explicit_manager,
|
||||
honcho_session_key="explicit-session",
|
||||
)
|
||||
)
|
||||
|
||||
assert result == {"result": ["explicit"]}
|
||||
explicit_manager.get_peer_card.assert_called_once_with("explicit-session")
|
||||
global_manager.get_peer_card.assert_not_called()
|
||||
Loading…
Add table
Add a link
Reference in a new issue